In an algorithm-selection stream where new solver classes appear, rehearsal-based class-incremental learning retains 82.3% accuracy across four solver classes, about 7% below an oracle that sees all data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Class Incremental Learning for Algorithm Selection
In an algorithm-selection stream where new solver classes appear, rehearsal-based class-incremental learning retains 82.3% accuracy across four solver classes, about 7% below an oracle that sees all data.